{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T08:28:15Z","timestamp":1793608095025,"version":"4.5.0"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100015401","name":"Key Research and Development Projects of Shaanxi Province","doi-asserted-by":"publisher","award":["2024GX-ZDCYL-02-07"],"award-info":[{"award-number":["2024GX-ZDCYL-02-07"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008049","name":"Xi'an Polytechnic University","doi-asserted-by":"publisher","award":["chx2026042"],"award-info":[{"award-number":["chx2026042"]}],"id":[{"id":"10.13039\/501100008049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2026AFD007"],"award-info":[{"award-number":["2026AFD007"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036007"],"award-info":[{"award-number":["62036007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2096"],"award-info":[{"award-number":["U22A2096"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971339"],"award-info":[{"award-number":["61971339"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.neunet.2026.109734","type":"journal-article","created":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T15:18:39Z","timestamp":1791645519000},"page":"109734","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["ConsistDiff: Training-free reinforcement learning for semantically consistent text-to-image generation"],"prefix":"10.1016","volume":"206","author":[{"given":"Junwei","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3770-017X","authenticated-orcid":false,"given":"Kaibing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8285-0743","authenticated-orcid":false,"given":"Xiaoyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109734_bib0001","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18370","article-title":"SpaText: Spatio-textual representation for controllable image generation","author":"Avrahami","year":"2023"},{"key":"10.1016\/j.neunet.2026.109734_bib0002","series-title":"International conference on learning representations","first-page":"4965","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2024"},{"key":"10.1016\/j.neunet.2026.109734_bib0003","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"22560","article-title":"MasaCtrl: Tuning-free mutual self-attention control for consistent image synthesis and editing","author":"Cao","year":"2023"},{"issue":"4","key":"10.1016\/j.neunet.2026.109734_bib0004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3592116","article-title":"Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models","volume":"42","author":"Chefer","year":"2023","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"10.1016\/j.neunet.2026.109734_bib0005","doi-asserted-by":"crossref","first-page":"79858","DOI":"10.52202\/075280-3497","article-title":"DPOK: Reinforcement learning for fine-tuning text-to-image diffusion models","volume":"36","author":"Fan","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109734_bib0006","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"Feng","year":"2023","journal-title":"International Conference on Learning Representations"},{"key":"10.1016\/j.neunet.2026.109734_bib0007","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A. H., Chechik, G., & Cohen-Or, D. (2022). An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv: 2208.01618."},{"key":"10.1016\/j.neunet.2026.109734_bib0008","doi-asserted-by":"crossref","first-page":"52132","DOI":"10.52202\/075280-2270","article-title":"GenEval: An object-focused framework for evaluating text-to-image alignment","volume":"36","author":"Ghosh","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109734_bib0009","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109734_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9380","article-title":"INITNO: Boosting text-to-image diffusion models via initial noise optimization","author":"Guo","year":"2024"},{"key":"10.1016\/j.neunet.2026.109734_bib0011","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"18401","article-title":"Spatial transport optimization by repositioning attention map for training-free text-to-image synthesis","author":"Han","year":"2025"},{"key":"10.1016\/j.neunet.2026.109734_bib0012","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., & Cohen-Or, D. (2022). Prompt-to-prompt image editing with cross attention control. arXiv: 2208.01626."},{"key":"10.1016\/j.neunet.2026.109734_bib0013","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4775","article-title":"Style aligned image generation via shared attention","author":"Hertz","year":"2024"},{"key":"10.1016\/j.neunet.2026.109734_bib0014","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109734_bib0015","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"23604","article-title":"Towards better alignment: Training diffusion models with reinforcement learning against sparse rewards","author":"Hu","year":"2025"},{"issue":"5","key":"10.1016\/j.neunet.2026.109734_bib0016","doi-asserted-by":"crossref","first-page":"3563","DOI":"10.1109\/TPAMI.2025.3531907","article-title":"T2i-CompBench++: An enhanced and comprehensive benchmark for compositional text-to-image generation","volume":"47","author":"Huang","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109734_bib0017","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1125","article-title":"Image-to-image translation with conditional adversarial networks","author":"Isola","year":"2017"},{"key":"10.1016\/j.neunet.2026.109734_bib0018","unstructured":"Kingma, D. P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv: 1312.6114."},{"key":"10.1016\/j.neunet.2026.109734_bib0019","series-title":"European conference on computer vision","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2026.109734_bib0020","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7817","article-title":"Towards understanding cross and self-attention in stable diffusion for text-guided image editing","author":"Liu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109734_bib0021","series-title":"Proceedings of the 2022 CHI conference on human factors in computing systems","first-page":"1","article-title":"Design guidelines for prompt engineering text-to-image generative models","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109734_bib0022","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7465","article-title":"FreeControl: Training-free spatial control of any text-to-image diffusion model with any condition","author":"Mo","year":"2024"},{"key":"10.1016\/j.neunet.2026.109734_bib0023","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"26627","article-title":"Dynamic prompt optimizing for text-to-image generation","author":"Mo","year":"2024"},{"key":"10.1016\/j.neunet.2026.109734_bib0024","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2021). GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv: 2112.10741."},{"key":"10.1016\/j.neunet.2026.109734_bib0025","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8764","article-title":"Zero-painter: Training-free layout control for text-to-image synthesis","author":"Ohanyan","year":"2024"},{"key":"10.1016\/j.neunet.2026.109734_bib0026","series-title":"ACM siggraph 2023 conference proceedings","first-page":"1","article-title":"Zero-shot image-to-image translation","author":"Parmar","year":"2023"},{"key":"10.1016\/j.neunet.2026.109734_bib0027","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"23051","article-title":"Localizing object-level shape variations with text-to-image diffusion models","author":"Patashnik","year":"2023"},{"key":"10.1016\/j.neunet.2026.109734_bib0028","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-conditional image generation with clip latents. 1(2), 3. arXiv: 2204.06125."},{"key":"10.1016\/j.neunet.2026.109734_bib0029","series-title":"International conference on machine learning","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021"},{"key":"10.1016\/j.neunet.2026.109734_bib0030","article-title":"Similarity-guided interaction and mismatched feature emphasis network for text-to-image person re-identification","volume":"667","author":"Ran","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109734_bib0031","series-title":"European conference on computer vision","first-page":"340","article-title":"Unveiling and mitigating memorization in text-to-image diffusion models through cross attention","author":"Ren","year":"2024"},{"key":"10.1016\/j.neunet.2026.109734_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.neunet.2026.109734_bib0033","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"22500","article-title":"DreamBooth: Fine tuning text-to-image diffusion models for subject-driven generation","author":"Ruiz","year":"2023"},{"key":"10.1016\/j.neunet.2026.109734_bib0034","doi-asserted-by":"crossref","first-page":"36479","DOI":"10.52202\/068431-2643","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109734_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9370","article-title":"Rethinking the spatial inconsistency in classifier-free diffusion guidance","author":"Shen","year":"2024"},{"key":"10.1016\/j.neunet.2026.109734_bib0036","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8921","article-title":"NoiseCollage: A layout-aware text-to-image diffusion model based on noise cropping and merging","author":"Shirakawa","year":"2024"},{"key":"10.1016\/j.neunet.2026.109734_bib0037","unstructured":"Song, J., Meng, C., & Ermon, S. (2020). Denoising diffusion implicit models. arXiv: 2010.02502."},{"key":"10.1016\/j.neunet.2026.109734_bib0038","series-title":"Reinforcement learning: An introduction","volume":"vol. 1","author":"Sutton","year":"1998"},{"key":"10.1016\/j.neunet.2026.109734_bib0039","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2647","article-title":"Object-centric image generation from layouts","volume":"vol. 35","author":"Sylvain","year":"2021"},{"key":"10.1016\/j.neunet.2026.109734_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1921","article-title":"Plug-and-play diffusion features for text-driven image-to-image translation","author":"Tumanyan","year":"2023"},{"key":"10.1016\/j.neunet.2026.109734_bib0041","series-title":"ACM siggraph 2023 conference proceedings","first-page":"1","article-title":"Sketch-guided text-to-image diffusion models","author":"Voynov","year":"2023"},{"key":"10.1016\/j.neunet.2026.109734_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8228","article-title":"Diffusion model alignment using direct preference optimization","author":"Wallace","year":"2024"},{"issue":"3","key":"10.1016\/j.neunet.2026.109734_bib0043","first-page":"279","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2026.109734_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128437","article-title":"From text to mask: Localizing entities using the attention of text-to-image diffusion models","volume":"610","author":"Xiao","year":"2024","journal-title":"Neurocomputing"},{"issue":"3","key":"10.1016\/j.neunet.2026.109734_bib0045","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1007\/s11263-024-02227-z","article-title":"FastComposer: Tuning-free multi-subject image generation with localized attention","volume":"133","author":"Xiao","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109734_bib0046","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"13220","article-title":"DyMO: Training-free diffusion model alignment with dynamic multi-objective scheduling","author":"Xie","year":"2025"},{"key":"10.1016\/j.neunet.2026.109734_bib0047","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1316","article-title":"AttnGAN: Fine-grained text to image generation with attentional generative adversarial networks","author":"Xu","year":"2018"},{"key":"10.1016\/j.neunet.2026.109734_bib0048","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"3525","article-title":"Data-driven loss functions for inference-time optimization in text-to-image","author":"Yiflach","year":"2026"},{"key":"10.1016\/j.neunet.2026.109734_bib0049","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"5907","article-title":"StackGAN: Text to photo-realistic image synthesis with stacked generative adversarial networks","author":"Zhang","year":"2017"},{"key":"10.1016\/j.neunet.2026.109734_bib0050","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3836","article-title":"Adding conditional control to text-to-image diffusion models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109734_bib0051","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2026.132912","article-title":"TFIGF: Fire data augmentation model based on text-to-image synthesis","volume":"675","author":"Zhao","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109734_bib0052","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"22490","article-title":"LayoutDiffusion: Controllable diffusion model for layout-to-image generation","author":"Zheng","year":"2023"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011895?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011895?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T07:53:43Z","timestamp":1793606023000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026011895"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":52,"alternative-id":["S0893608026011895"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109734","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ConsistDiff: Training-free reinforcement learning for semantically consistent text-to-image generation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109734","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109734"}}